System, method, and computer program product for inserting citations into a textual document

Abstract

Provided are systems, methods, and computer program products for inserting citations into a textual document. The method includes receiving a first user input identifying a portion of a textual document, generating a plurality of predicted citations based on comparing at least one string in the textual document associated with the portion of the textual document to at least a subset of source documents of a plurality of source documents with a model selected from a plurality of models based on the at least one string, each predicted citation of the plurality of predicted citations corresponding to at least one source document of the plurality of source documents, displaying, on a graphical user interface, the plurality of predicted citations, and inserting a predicted citation of the plurality of predicted citations into the portion of the textual document based on a second user input.

What is claimed is: 
     
       1. A computer-implemented method comprising:
 receiving, with at least one processor, a first user input identifying a portion of a textual document; 
 selecting, with at least one processor, a model from a plurality of models based on at least one string in the textual document associated with the portion of the textual document identified by the first user input; 
 generating, with at least one processor, a plurality of predicted citations based on comparing the at least one string to at least a subset of source documents of a plurality of source documents with the model, each predicted citation of the plurality of predicted citations corresponding to at least one source document of the plurality of source documents; 
 displaying, on a graphical user interface, the plurality of predicted citations; and 
 inserting, with at least one processor, a predicted citation of the plurality of predicted citations into the portion of the textual document based on a second user input associated with the plurality of predicted citations. 
 
     
     
       2. The computer-implemented method of  claim 1 , further comprising:
 receiving, from a user, a selection of the plurality of source documents. 
 
     
     
       3. The computer-implemented method of  claim 1 , wherein generating the plurality of predicted citations is further based on at least one of a machine-learning algorithm and a rule-based algorithm. 
     
     
       4. The computer-implemented method of  claim 1 , wherein generating the plurality of predicted citations comprises generating a predetermined number of predicted citations. 
     
     
       5. The computer-implemented method of  claim 1 , further comprising:
 ranking the plurality of predicted citations based on at least one of relevance and semantic similarity of the at least one string preceding the portion of the textual document compared to at least a portion of at least one source document. 
 
     
     
       6. The computer-implemented method of  claim 1 , wherein the first user input comprises selection of a button, and wherein the portion of the textual document is a position of a cursor within the textual document. 
     
     
       7. The computer-implemented method of  claim 1 , wherein the first user input comprises selection of the at least one string preceding the portion of the textual document. 
     
     
       8. The computer-implemented method of  claim 1 , further comprising:
 inserting, with at least one processor, a placeholder into the portion of the textual document based on the first user input, wherein inserting the predicted citation of the plurality of predicted citations into the portion of the textual document based on the second user input comprises replacing the placeholder with the predicted citation. 
 
     
     
       9. The computer-implemented method of  claim 1 , wherein the graphical user interface comprises a plurality of citation cards corresponding to the plurality of predicted citations, each citation card of the plurality of citation cards comprising at least one selectable option, and wherein the second user input comprises selection of the at least one selectable option. 
     
     
       10. The computer-implemented method of  claim 1 , wherein the graphical user interface comprises:
 a first selectable option configured to, in response to being selected, cause a predicted citation corresponding to the first selectable option to be inserted into the textual document; and 
 a second selectable option configured to, in response to being selected, cause a predicted citation corresponding to the second selectable option to be removed from the plurality of predicted citations. 
 
     
     
       11. The computer-implemented method of  claim 1 , wherein generating the plurality of predicted citations comprises:
 for each source document of the plurality of source documents, automatically selecting a model from the plurality of models based on a format of the source document; and 
 comparing the at least one string to each source document of the plurality of source documents with the model selected from the plurality of models for that source document. 
 
     
     
       12. The computer-implemented method of  claim 1 , further comprising:
 displaying, on the graphical user interface, a plurality of strings within the textual document relating to a selected predicted citation of the plurality of predicted citations. 
 
     
     
       13. The computer-implemented method of  claim 1 , further comprising:
 prompting a user to add a source document to the plurality of source documents. 
 
     
     
       14. The computer-implemented method of  claim 13 , further comprising:
 associating the predicted citations and/or a pattern of the predicted citations to the source document. 
 
     
     
       15. A system comprising at least one processor programmed or configured to:
 receive a first user input identifying a portion of a textual document; 
 select a model from a plurality of models based on at least one string in the textual document associated with the portion of the textual document identified by the first user input; 
 generate a plurality of predicted citations based on comparing the at least one string to at least a subset of source documents of a plurality of source documents with the model, each predicted citation of the plurality of predicted citations corresponding to at least one source document of the plurality of source documents; 
 display, on a graphical user interface, the plurality of predicted citations; and 
 insert a predicted citation of the plurality of predicted citations into the portion of the textual document based on a second user input associated with the plurality of predicted citations. 
 
     
     
       16. The system of  claim 15 , wherein the at least one processor is further programmed or configured to:
 receive, from a user, a selection of the plurality of source documents. 
 
     
     
       17. The system of  claim 15 , wherein generating the plurality of predicted citations is further based on at least one of a machine-learning algorithm and a rule-based algorithm. 
     
     
       18. The system of  claim 15 , wherein generating the plurality of predicted citations comprises generating a predetermined number of predicted citations. 
     
     
       19. The system of  claim 15 , wherein the at least one processor is further programmed or configured to:
 rank the plurality of predicted citations based on at least one of relevance and semantic similarity of the at least one string preceding the portion of the textual document compared to at least a portion of at least one source document. 
 
     
     
       20. The system of  claim 15 , wherein the first user input comprises selection of a button, and wherein the portion of the textual document is a position of a cursor within the textual document. 
     
     
       21. The system of  claim 15 , wherein the first user input comprises selection of the at least one string preceding the portion of the textual document. 
     
     
       22. The system of  claim 15 , wherein the at least one processor is further programmed or configured to:
 insert a placeholder into the portion of the textual document based on the first user input, wherein inserting the predicted citation of the plurality of predicted citations into the portion of the textual document based on the second user input comprises replacing the placeholder with the predicted citation. 
 
     
     
       23. The system of  claim 15 , wherein the graphical user interface comprises a plurality of citation cards corresponding to the plurality of predicted citations, each citation card of the plurality of citation cards comprising at least one selectable option, and wherein the second user input comprises selection of the at least one selectable option. 
     
     
       24. The system of  claim 15 , wherein the graphical user interface comprises:
 a first selectable option configured to, in response to being selected, cause a predicted citation corresponding to the first selectable option to be inserted into the textual document; and 
 a second selectable option configured to, in response to being selected, remove a predicted citation corresponding to the second selectable option to be removed from the plurality of predicted citations. 
 
     
     
       25. The system of  claim 24 , wherein the at least one processor generates the plurality of predicted citations by:
 for each source document of the plurality of source documents, automatically selecting a model from the plurality of models based on a format of the source document; and 
 comparing the at least one string to each source document of the plurality of source documents with the model selected from the plurality of models for that source document. 
 
     
     
       26. The system of  claim 15 , wherein the at least one processor is further programmed or configured to:
 display, on the graphical user interface, a plurality of strings within the textual document relating to a selected predicted citation of the plurality of predicted citations. 
 
     
     
       27. The system of  claim 15 , wherein the at least one processor is further programmed or configured to:
 prompt a user to add a source document to the plurality of source documents. 
 
     
     
       28. The system of  claim 27 , wherein the at least one processor is further programmed or configured to:
 associate the predicted citations and/or a pattern of the predicted citations to the source document. 
 
     
     
       29. A computer program product comprising at least one non-transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to:
 receive a first user input identifying a portion of a textual document; 
 select a model from a plurality of models based on at least one string in the textual document associated with the portion of the textual document identified by the first user input; 
 generate a plurality of predicted citations based on comparing the at least one string to at least a subset of source documents of a plurality of source documents with the model, each predicted citation of the plurality of predicted citations corresponding to at least one source document of the plurality of source documents; 
 display, on a graphical user interface, the plurality of predicted citations; and 
 insert a predicted citation of the plurality of predicted citations into the portion of the textual document based on a second user input associated with the plurality of predicted citations.